在怀疑COVID-19感染的患者的识别中无监督的自然语言处理
Rildo Pinto da Silva1, Juliana Tarossi Pollettini1, Antonio Pazin Filho1
1Faculdade de Medicina de Ribeirão Preto, Universidade de São Paulo, Ribeirão Preto, Brasil.
Cadernos de saude publica
|December 6, 2023
概括
识别患有后COVID-19综合征的患者对于有效的健康促进至关重要. 无监督的自然语言处理,特别是BERTopic,在快速识别这些患者方面显示出希望,尽管它也标记了其他条件.
科学领域:
- 医疗信息学 医疗信息学
- 医疗保健中的人工智能
- 公共卫生 公共卫生
背景情况:
- 后COVID-19综合征需要通过健康促进计划及时干预.
- 有效的患者鉴定对于节省成本的项目交付至关重要,特别是在流行病期间.
- 传统的识别方法往往不足以进行快速的大规模查.
研究的目的:
- 评估无监督自然语言处理 (NLP) 主题建模的有效性,用于识别疑似COVID-19患者.
- 为了比较BERTopic和Word2Vec模型在识别患者以促进COVID-19后的健康方面的性能.
主要方法:
- 一项描述性观察性研究分析了来自私人医疗保健提供者的105,008份事先授权.
- 应用了无监督的NLP主题建模,包括BERTopic和Word2Vec算法.
- BERTopic模型自动分组疾病,而Word2Vec则需要手动分析来识别COVID-19的主题.
主要成果:
- 该BERTopic模型 (超过1,000个授权/主题,没有文字处理) 识别了更严重的病例,平均成本为每份授权BRL 10,206,与人类分析相比,准确度为70%.
- 该模型确定1.9%的授权 (1987) 可能与健康促进计划相关,占总支出的5.4% (2030万 BRL).
- BERTopic还确定了其他疾病组 (骨科,精神病,癌症),与传统方法相比,经历了病例损失.
结论:
- BERTopic 作为一个有效的案例标签探索工具,可以为监督模型提供患者识别的信息.
- 通过NLP自动识别各种疾病群体,就健康数据隐私提出了重要的伦理考虑.
- NLP方法提供了一个有前途的途径,可以提高对符合健康促进计划的患者的快速和经济有效的识别.
更多相关视频
相关概念视频
Single Nucleotide Polymorphisms-SNPs
A single nucleotide polymorphism or SNP is a single nucleotide variation at a specific genomic position in a large population. It is the most prevalent type of sequence variation found in the human genome. Point mutations that occur in more than 1% of the population qualify as SNPs. These are present once every 1000 nucleotides on an average in the human genome. Replacement of a purine with another purine (A/G) or a pyrimidine with another pyrimidine (C/T) is known as a transition. In contrast,...
Rapid Identification of Pathogens
MALDI-TOF MS has transformed clinical microbiology by offering a rapid and reliable method for pathogen identification. The traditional approach to microbial identification typically involves time-consuming culture techniques and biochemical tests, which can delay the initiation of appropriate antimicrobial therapy. MALDI-TOF MS avoids these delays by using characteristic ribosomal protein mass patterns of microbial cells, enabling accurate species-level identification within minutes.Principle...


